Temporal grounding of text descriptions in videos is a central problem in
vision-language learning and video understanding. Existing methods often
prioritize accuracy over scalability -- they have been optimized for grounding
only a few text queries within short videos, and fail to scale up to long
videos with hundreds of queries. In this paper, we study the effect of
cross-modal fusion on the scalability of video grounding models. Our analysis
establishes late fusion as a more cost-effective fusion scheme for long-form
videos with many text queries. Moreover, it leads us to a novel, video-centric
sampling scheme for efficient training. Based on these findings, we present
SnAG, a simple baseline for scalable and accurate video grounding. Without
bells and whistles, SnAG is 43% more accurate and 1.5x faster than CONE, a
state of the art for long-form video grounding on the challenging MAD dataset,
while achieving highly competitive results on short videos.

在本文中，我们研究了跨模态融合对视频定位模型可扩展性的影响，通过分析发现，针对长视频和大量文本查询的情况，后期融合是一种更具成本效益的融合方案，并提出了一种基于视频的采样方案以实现高效训练。基于这些发现，我们提出了 SnAG，作为可扩展且准确的视频定位的简单基准模型，相较于现有的 CONE 方法在具有挑战性的 MAD 数据集上，在长视频上 SnAG 更准确且快速，同时在短视频上也取得了极具竞争力的结果。